Automatic cartoon generation method and system based on BBWC model and MCMC

Abstract

The invention provides an automatic cartoon generation method and system based on a BBWC model and an MCMC. The method comprises the following steps: firstly, carrying out entity labeling of an extended range on a Chinese data set; secondly, designing a BERTBiLSTM + WSCRF named entity recognition model, and training on the marked data set to recognize seven types of entities including names, placenames, organization names, common nouns, numerals, prepositions and nouns so as to obtain information such as foreground object types, background templates and the number and position relation of theforeground object types and the background templates; defining different scene templates to describe different scenes so as to supplement scene information; then selecting a proper template accordingto the previously obtained information; then, controlling the scene layout by an MCMC method to generate complete scene information; achieving seamless fusion of multiple image materials by a Poissonfusion algorithm; and finally, inputting the text into the final model, and automatically generating a cartoon conforming to semantics. According to the invention, the size, proportion and position relationship of each image can be reasonably controlled; Seamless fusion of multiple image materials can be realized.

Description

Technical field[0001]The present invention belongs to computer and information service technology, and particularly relates to a method and system for automatically generating semantic comics by recognizing Chinese natural language text.Background technique[0002]In modern life, people come into contact with thousands of image information from various channels every day, but even so, when people search for images, especially when the search sentence is a long sentence, it is still difficult to obtain in mainstream search engines. Images that fully comply with the semantic information of the search sentence. In this case, if you can realize the understanding of the input sentence and directly generate images that match the semantics, you will get more satisfactory results. Comics, as a kind of image category that is well-loved by the public, can be automatically generated by applying natural language processing, image synthesis and other technologies to automatically generate comics, ...

AI Technical Summary

Problems solved by technology

This method is simple to implement, but it will lose some details of the original image

Images